## pval_cutoff: 0.05
## lfc_cutoff: 1
## low_counts_cutoff: 10

General statistics

# Number of samples
length(counts_data)
## [1] 6
# Number of genes
nrow(counts_data)
## [1] 55487
# Total counts
colSums(counts_data)
## SRR13535276 SRR13535278 SRR13535280 SRR13535288 SRR13535290 SRR13535292 
##     3107284     2321609     3701956     7929174     6330905     3686532

Create DDS objects

# Create DESeqDataSet object
dds <- get_DESeqDataSet_obj(counts_data, ~ treatment)
## [1] TRUE
## [1] TRUE
## [1] "DESeqDataSet object of length 55487 with 0 metadata columns"
## [1] "DESeqDataSet object of length 15188 with 0 metadata columns"
colData(dds)
## DataFrame with 6 rows and 25 columns
##              Assay Type AvgSpotLen       Bases  BioProject    BioSample      Bytes Center Name     Consent DATASTORE filetype DATASTORE provider       DATASTORE region  Experiment treatment GEO_Accession (exp)          Instrument LibraryLayout LibrarySelection  LibrarySource     Organism    Platform                    label ReleaseDate Sample Name            source_name   SRA Study
##             <character>  <numeric>   <numeric> <character>  <character>  <numeric> <character> <character>        <character>        <character>            <character> <character>  <factor>         <character>         <character>   <character>      <character>    <character>  <character> <character>                 <factor>   <POSIXct> <character>            <character> <character>
## SRR13535276     RNA-Seq        300  8225466000 PRJNA694971 SAMN17588686 3252113587         GEO      public          fastq,sra         gs,ncbi,s3 gs.US,ncbi.public,s3..  SRX9943360         A          GSM5043430 Illumina HiSeq 2500        PAIRED             cDNA TRANSCRIPTOMIC Mus musculus    ILLUMINA in space without gravity  2021-09-09  GSM5043430 C2C12 proliferating ..   SRP303354
## SRR13535278     RNA-Seq        300  9203426700 PRJNA694971 SAMN17588684 3619152333         GEO      public          fastq,sra         gs,ncbi,s3 gs.US,ncbi.public,s3..  SRX9943362         A          GSM5043433 Illumina HiSeq 2500        PAIRED             cDNA TRANSCRIPTOMIC Mus musculus    ILLUMINA in space without gravity  2021-09-09  GSM5043433 C2C12 proliferating ..   SRP303354
## SRR13535280     RNA-Seq        300  9323939700 PRJNA694971 SAMN17588682 3735905901         GEO      public          fastq,sra         gs,ncbi,s3 gs.US,ncbi.public,s3..  SRX9943364         A          GSM5043436 Illumina HiSeq 2500        PAIRED             cDNA TRANSCRIPTOMIC Mus musculus    ILLUMINA in space without gravity  2021-09-09  GSM5043436 C2C12 proliferating ..   SRP303354
## SRR13535288     RNA-Seq        300 12863728500 PRJNA694971 SAMN17587373 5128876770         GEO      public          fastq,sra         gs,ncbi,s3 gs.US,ncbi.public,s3..  SRX9943372         C          GSM5043450 Illumina HiSeq 2500        PAIRED             cDNA TRANSCRIPTOMIC Mus musculus    ILLUMINA in space with gravity     2021-09-09  GSM5043450 C2C12 proliferating ..   SRP303354
## SRR13535290     RNA-Seq        300 12849825300 PRJNA694971 SAMN17587371 5136077921         GEO      public          fastq,sra         gs,ncbi,s3 gs.US,ncbi.public,s3..  SRX9943374         C          GSM5043454 Illumina HiSeq 2500        PAIRED             cDNA TRANSCRIPTOMIC Mus musculus    ILLUMINA in space with gravity     2021-09-09  GSM5043454 C2C12 proliferating ..   SRP303354
## SRR13535292     RNA-Seq        300 10569142200 PRJNA694971 SAMN17587369 4229018065         GEO      public          fastq,sra         gs,ncbi,s3 gs.US,ncbi.public,s3..  SRX9943376         C          GSM5043457 Illumina HiSeq 2500        PAIRED             cDNA TRANSCRIPTOMIC Mus musculus    ILLUMINA in space with gravity     2021-09-09  GSM5043457 C2C12 proliferating ..   SRP303354

Sample-to-sample comparisons

# Transform data (blinded rlog)
rld <- get_transformed_data(dds)

PCA plot

pca <- rld$pca
pca_df <- cbind(as.data.frame(colData(dds)) %>% rownames_to_column(var = 'name'), pca$x)
summary(pca)
## Importance of components:
##                            PC1     PC2     PC3     PC4    PC5       PC6
## Standard deviation     30.6369 29.5690 26.7750 23.5645 20.988 4.616e-14
## Proportion of Variance  0.2662  0.2480  0.2033  0.1575  0.125 0.000e+00
## Cumulative Proportion   0.2662  0.5142  0.7176  0.8750  1.000 1.000e+00
ggplot(pca_df, aes(x = PC1, y = PC2, color = label)) +
  geom_point() +
  geom_text(aes(label = name), position = position_nudge(y = -2), show.legend = F, size = 3) +
  scale_color_manual(values = colors_default) +
  scale_x_continuous(expand = c(0.2, 0))

Correlation heatmap

pheatmap(
  cor(rld$matrix),
  annotation_col = as.data.frame(colData(dds)) %>% select(label),
  color = brewer.pal(8, 'YlOrRd')
)

Wald test results

# DE analysis using Wald test
dds_full <- DESeq(dds)
colData(dds_full)
## DataFrame with 6 rows and 26 columns
##              Assay Type AvgSpotLen       Bases  BioProject    BioSample      Bytes Center Name     Consent DATASTORE filetype DATASTORE provider       DATASTORE region  Experiment treatment GEO_Accession (exp)          Instrument LibraryLayout LibrarySelection  LibrarySource     Organism    Platform                    label ReleaseDate Sample Name            source_name   SRA Study sizeFactor
##             <character>  <numeric>   <numeric> <character>  <character>  <numeric> <character> <character>        <character>        <character>            <character> <character>  <factor>         <character>         <character>   <character>      <character>    <character>  <character> <character>                 <factor>   <POSIXct> <character>            <character> <character>  <numeric>
## SRR13535276     RNA-Seq        300  8225466000 PRJNA694971 SAMN17588686 3252113587         GEO      public          fastq,sra         gs,ncbi,s3 gs.US,ncbi.public,s3..  SRX9943360         A          GSM5043430 Illumina HiSeq 2500        PAIRED             cDNA TRANSCRIPTOMIC Mus musculus    ILLUMINA in space without gravity  2021-09-09  GSM5043430 C2C12 proliferating ..   SRP303354   0.679518
## SRR13535278     RNA-Seq        300  9203426700 PRJNA694971 SAMN17588684 3619152333         GEO      public          fastq,sra         gs,ncbi,s3 gs.US,ncbi.public,s3..  SRX9943362         A          GSM5043433 Illumina HiSeq 2500        PAIRED             cDNA TRANSCRIPTOMIC Mus musculus    ILLUMINA in space without gravity  2021-09-09  GSM5043433 C2C12 proliferating ..   SRP303354   0.949141
## SRR13535280     RNA-Seq        300  9323939700 PRJNA694971 SAMN17588682 3735905901         GEO      public          fastq,sra         gs,ncbi,s3 gs.US,ncbi.public,s3..  SRX9943364         A          GSM5043436 Illumina HiSeq 2500        PAIRED             cDNA TRANSCRIPTOMIC Mus musculus    ILLUMINA in space without gravity  2021-09-09  GSM5043436 C2C12 proliferating ..   SRP303354   0.775037
## SRR13535288     RNA-Seq        300 12863728500 PRJNA694971 SAMN17587373 5128876770         GEO      public          fastq,sra         gs,ncbi,s3 gs.US,ncbi.public,s3..  SRX9943372         C          GSM5043450 Illumina HiSeq 2500        PAIRED             cDNA TRANSCRIPTOMIC Mus musculus    ILLUMINA in space with gravity     2021-09-09  GSM5043450 C2C12 proliferating ..   SRP303354   1.903462
## SRR13535290     RNA-Seq        300 12849825300 PRJNA694971 SAMN17587371 5136077921         GEO      public          fastq,sra         gs,ncbi,s3 gs.US,ncbi.public,s3..  SRX9943374         C          GSM5043454 Illumina HiSeq 2500        PAIRED             cDNA TRANSCRIPTOMIC Mus musculus    ILLUMINA in space with gravity     2021-09-09  GSM5043454 C2C12 proliferating ..   SRP303354   1.293435
## SRR13535292     RNA-Seq        300 10569142200 PRJNA694971 SAMN17587369 4229018065         GEO      public          fastq,sra         gs,ncbi,s3 gs.US,ncbi.public,s3..  SRX9943376         C          GSM5043457 Illumina HiSeq 2500        PAIRED             cDNA TRANSCRIPTOMIC Mus musculus    ILLUMINA in space with gravity     2021-09-09  GSM5043457 C2C12 proliferating ..   SRP303354   0.820641
# Wald test results
res <- results(
  dds_full,
  contrast = c('treatment', condition, control),
  alpha = pval_cutoff
)
res
## log2 fold change (MLE): treatment A vs C 
## Wald test p-value: treatment A vs C 
## DataFrame with 15188 rows and 6 columns
##                     baseMean log2FoldChange     lfcSE      stat     pvalue      padj
##                    <numeric>      <numeric> <numeric> <numeric>  <numeric> <numeric>
## ENSMUSG00000098104   5.46468       1.192223  0.980393  1.216066   0.223960        NA
## ENSMUSG00000103922   2.19055      -0.264400  2.004893 -0.131877   0.895081        NA
## ENSMUSG00000033845 170.96155      -0.410660  0.542059 -0.757592   0.448695  0.897547
## ENSMUSG00000102275   2.42483       0.445773  1.599930  0.278620   0.780536        NA
## ENSMUSG00000025903 145.03192      -0.144159  0.305941 -0.471199   0.637499  0.941449
## ...                      ...            ...       ...       ...        ...       ...
## ENSMUSG00000061654  89.83965      -5.639498  3.758749 -1.500366         NA        NA
## ENSMUSG00000079834  57.89103      -0.191890  0.531060 -0.361333 0.71785066  0.959205
## ENSMUSG00000095041 282.40751      -0.142151  0.680850 -0.208784 0.83461669  0.980566
## ENSMUSG00000063897  38.58802       0.249799  0.436318  0.572515 0.56697292  0.928150
## ENSMUSG00000095742   8.84404       2.668715  0.872880  3.057370 0.00223289  0.138082
mcols(res)
## DataFrame with 6 rows and 2 columns
##                        type            description
##                 <character>            <character>
## baseMean       intermediate mean of normalized c..
## log2FoldChange      results log2 fold change (ML..
## lfcSE               results standard error: trea..
## stat                results Wald statistic: trea..
## pvalue              results Wald test p-value: t..
## padj                results   BH adjusted p-values
summary(res)
## 
## out of 15188 with nonzero total read count
## adjusted p-value < 0.05
## LFC > 0 (up)       : 9, 0.059%
## LFC < 0 (down)     : 72, 0.47%
## outliers [1]       : 179, 1.2%
## low counts [2]     : 3527, 23%
## (mean count < 8)
## [1] see 'cooksCutoff' argument of ?results
## [2] see 'independentFiltering' argument of ?results
plotDispEsts(dds_full)

Summary details

# Upregulated genes (LFC > 0)
res_sig_df %>% filter(log2FoldChange > 0)
# Downregulated genes (LFC < 0)
res_sig_df %>% filter(log2FoldChange < 0)
# Outliers (pvalue and padj are NA)
res[which(is.na(res$pvalue)), ]
## log2 fold change (MLE): treatment A vs C 
## Wald test p-value: treatment A vs C 
## DataFrame with 179 rows and 6 columns
##                     baseMean log2FoldChange     lfcSE      stat    pvalue      padj
##                    <numeric>      <numeric> <numeric> <numeric> <numeric> <numeric>
## ENSMUSG00000103509   9.61465       -4.46237   2.56030  -1.74291        NA        NA
## ENSMUSG00000079554  38.15136       -6.55179   2.04362  -3.20597        NA        NA
## ENSMUSG00000085842  32.45798        3.92441   2.26209   1.73486        NA        NA
## ENSMUSG00000103553  13.01159       -4.72236   2.90747  -1.62422        NA        NA
## ENSMUSG00000102425  25.59836        6.42741   2.37852   2.70227        NA        NA
## ...                      ...            ...       ...       ...       ...       ...
## ENSMUSG00000024867   25.1588       -1.33806   1.33535  -1.00203        NA        NA
## ENSMUSG00000117704   65.4156       -4.86080   1.98458  -2.44928        NA        NA
## ENSMUSG00000025089   56.0190       -1.68541   1.37462  -1.22610        NA        NA
## ENSMUSG00000048029   24.8196       -6.69369   3.90828  -1.71269        NA        NA
## ENSMUSG00000061654   89.8396       -5.63950   3.75875  -1.50037        NA        NA
# Low counts (only padj is NA)
res[which(is.na(res$padj) & !is.na(res$pvalue)), ]
## log2 fold change (MLE): treatment A vs C 
## Wald test p-value: treatment A vs C 
## DataFrame with 3527 rows and 6 columns
##                     baseMean log2FoldChange     lfcSE       stat    pvalue      padj
##                    <numeric>      <numeric> <numeric>  <numeric> <numeric> <numeric>
## ENSMUSG00000098104   5.46468       1.192223  0.980393   1.216066  0.223960        NA
## ENSMUSG00000103922   2.19055      -0.264400  2.004893  -0.131877  0.895081        NA
## ENSMUSG00000102275   2.42483       0.445773  1.599930   0.278620  0.780536        NA
## ENSMUSG00000103280   3.07360      -0.631912  1.204891  -0.524456  0.599961        NA
## ENSMUSG00000033740   2.71686      -2.681434  2.566083  -1.044952  0.296045        NA
## ...                      ...            ...       ...        ...       ...       ...
## ENSMUSG00000064342   5.31912     -0.3225041  1.294467 -0.2491404  0.803252        NA
## ENSMUSG00000064344   5.55025     -0.7333533  1.329458 -0.5516184  0.581210        NA
## ENSMUSG00000064349   4.21295     -0.0813581  1.110029 -0.0732937  0.941572        NA
## ENSMUSG00000064358   2.53260      1.6658901  1.341770  1.2415618  0.214398        NA
## ENSMUSG00000064369   6.67428      0.8693932  0.980304  0.8868608  0.375154        NA

Shrunken LFC results

plotMA(res)

# Shrunken LFC results
res_shrunken <- lfcShrink(
  dds_full,
  coef = str_c('treatment_', condition, '_vs_', control),
  type = 'apeglm'
)
res_shrunken
## log2 fold change (MAP): treatment A vs C 
## Wald test p-value: treatment A vs C 
## DataFrame with 15188 rows and 5 columns
##                     baseMean log2FoldChange     lfcSE     pvalue      padj
##                    <numeric>      <numeric> <numeric>  <numeric> <numeric>
## ENSMUSG00000098104   5.46468     0.04484650  0.196771   0.223960        NA
## ENSMUSG00000103922   2.19055    -0.00240059  0.191823   0.895081        NA
## ENSMUSG00000033845 170.96155    -0.04683613  0.188929   0.448695  0.897547
## ENSMUSG00000102275   2.42483     0.00639198  0.191482   0.780536        NA
## ENSMUSG00000025903 145.03192    -0.04144011  0.167089   0.637499  0.941449
## ...                      ...            ...       ...        ...       ...
## ENSMUSG00000061654  89.83965    -0.00740276  0.192885         NA        NA
## ENSMUSG00000079834  57.89103    -0.02214728  0.182797 0.71785066  0.959205
## ENSMUSG00000095041 282.40751    -0.01024471  0.185774 0.83461669  0.980566
## ENSMUSG00000063897  38.58802     0.04167765  0.181520 0.56697292  0.928150
## ENSMUSG00000095742   8.84404     1.89965145  1.103225 0.00223289  0.138082
plotMA(res_shrunken)

mcols(res_shrunken)
## DataFrame with 5 rows and 2 columns
##                        type            description
##                 <character>            <character>
## baseMean       intermediate mean of normalized c..
## log2FoldChange      results log2 fold change (MA..
## lfcSE               results posterior SD: treatm..
## pvalue              results Wald test p-value: t..
## padj                results   BH adjusted p-values
summary(res_shrunken, alpha = pval_cutoff)
## 
## out of 15188 with nonzero total read count
## adjusted p-value < 0.05
## LFC > 0 (up)       : 9, 0.059%
## LFC < 0 (down)     : 72, 0.47%
## outliers [1]       : 179, 1.2%
## low counts [2]     : 3527, 23%
## (mean count < 8)
## [1] see 'cooksCutoff' argument of ?results
## [2] see 'independentFiltering' argument of ?results

Summary details

# Upregulated genes (LFC > 0)
res_shrunken_sig_df %>% filter(log2FoldChange > 0)
# Downregulated genes (LFC < 0)
res_shrunken_sig_df %>% filter(log2FoldChange < 0)
# Outliers (pvalue and padj are NA)
res_shrunken[which(is.na(res_shrunken$pvalue)), ]
## log2 fold change (MAP): treatment A vs C 
## Wald test p-value: treatment A vs C 
## DataFrame with 179 rows and 5 columns
##                     baseMean log2FoldChange     lfcSE    pvalue      padj
##                    <numeric>      <numeric> <numeric> <numeric> <numeric>
## ENSMUSG00000103509   9.61465     -0.0173337  0.193723        NA        NA
## ENSMUSG00000079554  38.15136     -0.0340687  0.197165        NA        NA
## ENSMUSG00000085842  32.45798      0.0191760  0.193938        NA        NA
## ENSMUSG00000103553  13.01159     -0.0129806  0.193266        NA        NA
## ENSMUSG00000102425  25.59836      0.0226261  0.194639        NA        NA
## ...                      ...            ...       ...       ...       ...
## ENSMUSG00000024867   25.1588    -0.02592654  0.193589        NA        NA
## ENSMUSG00000117704   65.4156    -0.02680544  0.195361        NA        NA
## ENSMUSG00000025089   56.0190    -0.02975094  0.194687        NA        NA
## ENSMUSG00000048029   24.8196    -0.00752951  0.192901        NA        NA
## ENSMUSG00000061654   89.8396    -0.00740276  0.192885        NA        NA
# Low counts (only padj is NA)
res_shrunken[which(is.na(res_shrunken$padj) & !is.na(res_shrunken$pvalue)), ]
## log2 fold change (MAP): treatment A vs C 
## Wald test p-value: treatment A vs C 
## DataFrame with 3527 rows and 5 columns
##                     baseMean log2FoldChange     lfcSE    pvalue      padj
##                    <numeric>      <numeric> <numeric> <numeric> <numeric>
## ENSMUSG00000098104   5.46468     0.04484650  0.196771  0.223960        NA
## ENSMUSG00000103922   2.19055    -0.00240059  0.191823  0.895081        NA
## ENSMUSG00000102275   2.42483     0.00639198  0.191482  0.780536        NA
## ENSMUSG00000103280   3.07360    -0.01599164  0.191196  0.599961        NA
## ENSMUSG00000033740   2.71686    -0.01341707  0.193044  0.296045        NA
## ...                      ...            ...       ...       ...       ...
## ENSMUSG00000064342   5.31912    -0.00681405  0.190794  0.803252        NA
## ENSMUSG00000064344   5.55025    -0.01463269  0.191602  0.581210        NA
## ENSMUSG00000064349   4.21295    -0.00230978  0.189871  0.941572        NA
## ENSMUSG00000064358   2.53260     0.03393515  0.195227  0.214398        NA
## ENSMUSG00000064369   6.67428     0.03247049  0.193121  0.375154        NA

Visualizing results

Heatmaps

# Plot normalized counts (z-scores)
pheatmap(counts_sig_norm[2:7], 
         color = brewer.pal(8, 'YlOrRd'), 
         cluster_rows = T, 
         show_rownames = F,
         annotation_col = as.data.frame(colData(dds)) %>% select(label),
         border_color = NA,
         fontsize = 10,
         scale = 'row',
         fontsize_row = 10, 
         height = 20)

# Plot log-transformed counts
pheatmap(counts_sig_log[2:7], 
         color = rev(brewer.pal(8, 'RdYlBu')), 
         cluster_rows = T, 
         show_rownames = F,
         annotation_col = as.data.frame(colData(dds)) %>% select(label),
         border_color = NA,
         fontsize = 10,
         fontsize_row = 10, 
         height = 20)

# Plot log-transformed counts (top 24 DE genes)
pheatmap(counts_sig_log %>% filter(ensembl_gene_id %in% (res_sig_df %>% head(24))$ensembl_gene_id) %>% select(-ensembl_gene_id) %>% column_to_rownames(var = 'mgi_symbol'),
         color = rev(brewer.pal(8, 'RdYlBu')), 
         cluster_rows = T, 
         show_rownames = T,
         annotation_col = as.data.frame(colData(dds)) %>% select(label), 
         fontsize = 10,
         fontsize_row = 10, 
         height = 20)

Volcano plots

# Unshrunken LFC
res_df %>% 
  mutate(
    sig_threshold = if_else(
      padj < pval_cutoff & abs(log2FoldChange) >= lfc_cutoff,
      if_else(log2FoldChange > 0, 'DE-up', 'DE-down'),
      'non-DE'
    )
  ) %>% 
  filter(!is.na(sig_threshold)) %>% 
  ggplot() +
  geom_point(aes(x = log2FoldChange, y = -log10(padj), colour = sig_threshold)) +
  scale_color_manual(values = c('blue', 'red', 'gray')) +
  xlab('log2 fold change') + 
  ylab('-log10 adjusted p-value')

# Shrunken LFC
res_shrunken_df %>% 
  mutate(
    sig_threshold = if_else(
      padj < pval_cutoff & abs(log2FoldChange) >= lfc_cutoff,
      if_else(log2FoldChange > 0, 'DE-up', 'DE-down'),
      'non-DE'
    )
  ) %>% 
  filter(!is.na(sig_threshold)) %>% 
  ggplot() +
  geom_point(aes(x = log2FoldChange, y = -log10(padj), colour = sig_threshold)) +
  scale_color_manual(values = c('blue', 'red', 'gray')) +
  xlab('log2 fold change') + 
  ylab('-log10 adjusted p-value')

GSEA (all)

Hallmark genesets

# Shrunken LFC
get_fgsea_res(rank_lfc, mm_h) %>% plot_enrichment_table(rank_lfc, mm_h)

# Wald stat
get_fgsea_res(rank_stat, mm_h) %>% plot_enrichment_table(rank_stat, mm_h)

# Rank: sign(LFC) * -log10(pvalue)
get_fgsea_res(rank_pval, mm_h) %>% plot_enrichment_table(rank_pval, mm_h)

GO biological process

# Shrunken LFC
get_fgsea_res(rank_lfc, mm_c5_bp) %>% plot_enrichment_table(rank_lfc, mm_c5_bp)

# Wald stat
get_fgsea_res(rank_stat, mm_c5_bp) %>% plot_enrichment_table(rank_stat, mm_c5_bp)

# Rank: sign(LFC) * -log10(pvalue)
get_fgsea_res(rank_pval, mm_c5_bp) %>% plot_enrichment_table(rank_pval, mm_c5_bp)

GO cellular component

# Shrunken LFC
get_fgsea_res(rank_lfc, mm_c5_cc) %>% plot_enrichment_table(rank_lfc, mm_c5_cc)

# Wald stat
get_fgsea_res(rank_stat, mm_c5_cc) %>% plot_enrichment_table(rank_stat, mm_c5_cc)

# Rank: sign(LFC) * -log10(pvalue)
get_fgsea_res(rank_pval, mm_c5_cc) %>% plot_enrichment_table(rank_pval, mm_c5_cc)

GO molecular function

# Shrunken LFC
get_fgsea_res(rank_lfc, mm_c5_mf) %>% plot_enrichment_table(rank_lfc, mm_c5_mf)

# Wald stat
get_fgsea_res(rank_stat, mm_c5_mf) %>% plot_enrichment_table(rank_stat, mm_c5_mf)

# Rank: sign(LFC) * -log10(pvalue)
get_fgsea_res(rank_pval, mm_c5_mf) %>% plot_enrichment_table(rank_pval, mm_c5_mf)

GSEA (DE)

Hallmark genesets

# Shrunken LFC
get_fgsea_res(rank_lfc, mm_h) %>% plot_enrichment_table(rank_lfc, mm_h)

# Wald stat
get_fgsea_res(rank_stat, mm_h) %>% plot_enrichment_table(rank_stat, mm_h)

# Rank: sign(LFC) * -log10(pvalue)
get_fgsea_res(rank_pval, mm_h) %>% plot_enrichment_table(rank_pval, mm_h)

GO biological process

# Shrunken LFC
get_fgsea_res(rank_lfc, mm_c5_bp) %>% plot_enrichment_table(rank_lfc, mm_c5_bp)

# Wald stat
get_fgsea_res(rank_stat, mm_c5_bp) %>% plot_enrichment_table(rank_stat, mm_c5_bp)

# Rank: sign(LFC) * -log10(pvalue)
get_fgsea_res(rank_pval, mm_c5_bp) %>% plot_enrichment_table(rank_pval, mm_c5_bp)

GO cellular component

# Shrunken LFC
get_fgsea_res(rank_lfc, mm_c5_cc) %>% plot_enrichment_table(rank_lfc, mm_c5_cc)

# Wald stat
get_fgsea_res(rank_stat, mm_c5_cc) %>% plot_enrichment_table(rank_stat, mm_c5_cc)

# Rank: sign(LFC) * -log10(pvalue)
get_fgsea_res(rank_pval, mm_c5_cc) %>% plot_enrichment_table(rank_pval, mm_c5_cc)

GO molecular function

# Shrunken LFC
get_fgsea_res(rank_lfc, mm_c5_mf) %>% plot_enrichment_table(rank_lfc, mm_c5_mf)

# Wald stat
get_fgsea_res(rank_stat, mm_c5_mf) %>% plot_enrichment_table(rank_stat, mm_c5_mf)

# Rank: sign(LFC) * -log10(pvalue)
get_fgsea_res(rank_pval, mm_c5_mf) %>% plot_enrichment_table(rank_pval, mm_c5_mf)

System info

sessionInfo()
## R version 4.1.0 (2021-05-18)
## Platform: x86_64-conda-linux-gnu (64-bit)
## Running under: CentOS Linux 7 (Core)
## 
## Matrix products: default
## BLAS/LAPACK: /home/chan/mRNA_seq_pipeline/.snakemake/conda/9a19315a020c824d12f8055f7c009b0f/lib/libopenblasp-r0.3.18.so
## 
## locale:
##  [1] LC_CTYPE=en_US.UTF-8       LC_NUMERIC=C               LC_TIME=en_US.UTF-8        LC_COLLATE=en_US.UTF-8     LC_MONETARY=en_US.UTF-8    LC_MESSAGES=en_US.UTF-8    LC_PAPER=en_US.UTF-8       LC_NAME=C                  LC_ADDRESS=C               LC_TELEPHONE=C             LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C       
## 
## attached base packages:
## [1] stats4    stats     graphics  grDevices utils     datasets  methods   base     
## 
## other attached packages:
##  [1] fgsea_1.20.0                RColorBrewer_1.1-2          pheatmap_1.0.12             DESeq2_1.34.0               SummarizedExperiment_1.24.0 Biobase_2.54.0              MatrixGenerics_1.6.0        matrixStats_0.61.0          GenomicRanges_1.46.0        GenomeInfoDb_1.30.0         IRanges_2.28.0              S4Vectors_0.32.0            BiocGenerics_0.40.0         scales_1.1.1                forcats_0.5.1               stringr_1.4.0               dplyr_1.0.7                 purrr_0.3.4                 readr_2.1.1                 tidyr_1.1.4                 tibble_3.1.6                ggplot2_3.3.5               tidyverse_1.3.1            
## 
## loaded via a namespace (and not attached):
##  [1] colorspace_2.0-2       ellipsis_0.3.2         XVector_0.34.0         fs_1.5.1               rstudioapi_0.13        farver_2.1.0           bit64_4.0.5            mvtnorm_1.1-3          AnnotationDbi_1.56.1   fansi_0.4.2            apeglm_1.16.0          lubridate_1.8.0        xml2_1.3.3             splines_4.1.0          cachem_1.0.6           geneplotter_1.72.0     knitr_1.35             jsonlite_1.7.2         broom_0.7.10           annotate_1.72.0        dbplyr_2.1.1           png_0.1-7              compiler_4.1.0         httr_1.4.2             backports_1.4.0        assertthat_0.2.1       Matrix_1.3-4           fastmap_1.1.0          cli_3.1.0              htmltools_0.5.2        tools_4.1.0            coda_0.19-4            gtable_0.3.0           glue_1.5.1             GenomeInfoDbData_1.2.7 fastmatch_1.1-3        Rcpp_1.0.7             bbmle_1.0.24           cellranger_1.1.0       jquerylib_0.1.4        vctrs_0.3.8            Biostrings_2.62.0      xfun_0.28              rvest_1.0.2            lifecycle_1.0.1        XML_3.99-0.8           MASS_7.3-54            zlibbioc_1.40.0        vroom_1.5.7            hms_1.1.1              parallel_4.1.0         yaml_2.2.1             memoise_2.0.1          gridExtra_2.3          emdbook_1.3.12         bdsmatrix_1.3-4        stringi_1.7.6          RSQLite_2.2.8          highr_0.9              genefilter_1.76.0      BiocParallel_1.28.0    rlang_0.4.12           pkgconfig_2.0.3        bitops_1.0-7           evaluate_0.14          lattice_0.20-45        labeling_0.4.2         bit_4.0.4              tidyselect_1.1.1       plyr_1.8.6             magrittr_2.0.1         R6_2.5.1               generics_0.1.1         DelayedArray_0.20.0    DBI_1.1.1              pillar_1.6.4           haven_2.4.3            withr_2.4.3            survival_3.2-13        KEGGREST_1.34.0        RCurl_1.98-1.5         modelr_0.1.8           crayon_1.4.2           utf8_1.2.2             tzdb_0.2.0             rmarkdown_2.11         locfit_1.5-9.4         grid_4.1.0             readxl_1.3.1           data.table_1.14.2      blob_1.2.2             reprex_2.0.1           digest_0.6.29          xtable_1.8-4           numDeriv_2016.8-1.1    munsell_0.5.0